اپنے ایجنٹ کے لیے موزوں صلاحیت تلاش کریں۔
Fetches and references LangGraph Python documentation to build stateful agents, create multi-agent workflows, and implement human-in-the-loop patterns. Use when the user asks about LangGraph, graph agents, state machines, agent orchestration, LangGraph API, or needs LangGraph implementation guidance.
Chart selection guidance, Python visualization code patterns, design principles, and accessibility considerations for creating effective data visualizations.
Skill for BigQuery AI and Machine Learning queries using standard SQL and `AI.*` functions (preferred over dedicated tools).
A skill that provides weather information based on reference data.
A skill that provides weather information based on reference data.
Python SDK patterns for Opik. Use when working in sdks/python, on SDK APIs, integrations, or message processing.
Use when working with the OpenAI API (Responses API) or OpenAI platform features (tools, streaming, Realtime API, auth, models, rate limits, MCP) and you need authoritative, up-to-date documentation (schemas, examples, limits, edge cases). Prefer the OpenAI Developer Documentation MCP server tools when available; otherwise guide the user to enable `openaiDeveloperDocs`.
Run python examples in auto mode with logging, rerun helpers, and background control.
Perform a release-readiness review by locating the previous release tag from remote tags and auditing the diff (e.g., v1.2.3...<commit>) for breaking changes, regressions, improvement opportunities, and risks before releasing openai-agents-python.
Create a PR title and draft description after substantive code changes are finished. Trigger when wrapping up a moderate-or-larger change (runtime code, tests, build config, docs with behavior impact) and you need the PR-ready summary block with change summary plus PR draft text.
Analyze main branch implementation and configuration to find missing, incorrect, or outdated documentation in docs/. Use when asked to audit doc coverage, sync docs with code, or propose doc updates/structure changes. Only update English docs under docs/** and never touch translated docs under docs/ja, docs/ko, or docs/zh. Provide a report and ask for approval before editing docs.
Run the mandatory verification stack when changes affect runtime code, tests, or build/test behavior in the OpenAI Agents Python repository.
Improve test coverage in the OpenAI Agents Python repository: run `make coverage`, inspect coverage artifacts, identify low-coverage files, propose high-impact tests, and confirm with the user before writing tests.
Write and review secure modern Python code following current best practices. Use when auditing Python applications for security issues, implementing secure patterns with modern Python features (3.10+), reviewing Python web frameworks, or hardening Python deployments.
Application security testing toolkit from the Trail of Bits Testing Handbook. Helps the agent set up fuzzing campaigns, write fuzz harnesses, run coverage-guided fuzzers (libFuzzer, AFL++, cargo-fuzz, Atheris, Ruzzy), and triage crashes. Covers memory-safety sanitizers (AddressSanitizer, UBSan, MSan), static analysis with Semgrep and CodeQL, cryptographic validation using Wycheproof test vectors, and constant-time verification. Use when testing C, C++, Rust, Python, or Ruby code for vulnerabilities, improving code coverage, building seed corpora, creating fuzzing dictionaries, overcoming fuzzing obstacles, or integrating security checks into CI/CD with OSS-Fuzz.
Atheris is a coverage-guided Python fuzzing framework built on libFuzzer for finding bugs, crashes, and security vulnerabilities in pure Python code and Python C extensions. It provides AddressSanitizer integration for detecting memory corruption, buffer overflows, and use-after-free errors. Assists with writing fuzz harnesses, configuring sanitizers, managing corpora, running fuzzing campaigns, and setting up Docker-based fuzzing environments. Covers instrumentation of Python imports, parallel fuzzing with workers, corpus minimization, and troubleshooting common issues like LD_PRELOAD configuration and compiler flag setup.
Guides the agent through CodeQL static analysis, including creating databases, writing custom QL queries, running interprocedural data flow and control flow analysis, detecting security vulnerabilities, setting up GitHub Actions code scanning, and managing query packs. Covers C, C++, Go, Java, Kotlin, JavaScript, TypeScript, Python, Ruby, Swift, and SARIF output processing.
The agent uses OSS-Fuzz, Google's free distributed continuous fuzzing platform, to build, run, and manage fuzzing infrastructure for open-source projects. It configures project enrollment files (project.yaml, Dockerfile, build.sh), builds fuzzers locally with helper.py, runs harnesses with AddressSanitizer and other sanitizers, generates coverage reports, and troubleshoots build failures. The agent applies this technique when setting up continuous fuzzing for C/C++, Rust, Python (Atheris), or Go projects, reproducing crashes from OSS-Fuzz bug reports, analyzing Fuzz Introspector coverage data, evaluating criticality scores for project acceptance, or hosting a private OSS-Fuzz instance for closed-source targets that need Docker-based fuzzing infrastructure with libFuzzer or AFL++ engines.
Remote-control tmux sessions for interactive CLIs by sending keystrokes, capturing pane output, and managing terminal multiplexer windows. Enables parallel coding-agent orchestration, background process management, and REPL interaction via sockets. Use when the agent needs to launch, monitor, or coordinate long-running terminal processes, run multiple agents in parallel, interact with a Python REPL, or scrape live shell output from a persistent session.
